1. Prof. Dr. Hendrik Drachsler @hdrachsler
Towards Tangible Trusted Learning Analytics
Learning Analytics Workshop, 08.04.2019,
TU Delft, The Netherlands
2. WhoAmI
Hendrik Drachsler
Professor of
Educational Technologies
Research topics
Recommender Systems
Learning Analytics
Multimodal Data for learning
Computational Psychometrics
Application domains
Schools
HEI
Medical education
3. Educational Technologies Team
Nicole Elker
Function:
Management
Assistent
Daniel
Biedermann
Function:
PhD student
Sambit
Praharaj
Function:
PhD student
George
Ciordas-
Hertel
Function:
PhD student
Sebastian
Wollny
Function:
PhD student
Dr. Jan
Schneider
Function:
PostDoc
Atezaz
Ahmad
Function:
PhD student
Ioana
Jivet
Function:
PhD student
Daniele
Dimitri
Function:
PhD student
Marcel
Schmitz
Function:
PhD student
Dr. Maren
Scheffel
Function:
PostDoc
Hector
Pijeira Diaz
Function:
PhD student
Superhero’s
4. 1. Definition
of trust and
LA
2. Fears of
Learning
Analytics
4. Approaches
towards
Trusted Learning
Analytics
3. Human-
Centered
Design
Lecture structure
6. Greller, W. & Drachsler, H. (2012). Turning Learning into Numbers. Toward a Generic
Framework for Learning Analytics. Journal of Educational Technology & Society.
http://ifets.info/journals/15_3/4.pdf
Learning Analytics
7. Greller, W. & Drachsler, H. (2012). Turning Learning into Numbers. Toward a Generic
Framework for Learning Analytics. Journal of Educational Technology & Society.
http://ifets.info/journals/15_3/4.pdf
Learning Analytics
8. Sophistican model
Siemens, G., Dawson, S., & Lynch, G. (2014). Improving the Quality and Productivity of the
Higher Education Sector – Policy and Strategy for Systems-Level Deployment of
Learning Analytics. Canberra, Australia: Office of Learning and Teaching, Australian
Government. Retrieved from http://solaresearch.org/Policy_Strategy_Analytics.pdf
1
2
3
4
5
Learning Analytics
11. Oxford Dictionary
Trust is about a firm belief in the
reliability, truth, or ability of someone or
something.
A trustful relation is mutually
based on:
• openness
• truth
• reliability
• integrity
• belief
• faith
• freedom of suspicion
Picture by Terry Johnston
https://www.flickr.com/photos/powerbooktrance/466709245/
Multiple definitions of Trust
Trust =
a multidimensional and
multidisciplinary construct
Various Contexts
• oneself and others
• organizations
• intelligent systems
• automation
• money or political power
12. Niklas Luhmann. Trust and power. John Willey & Sons (1979).
A definition of Trust
Luhmann defined ‘TRUST’ as a way
to cope with risk, complexity, and a
lack of system understanding.
For Luhmann the concept of trust
compensates for insufficient
capabilities for full understanding
the complexity of the world.
Picture by:
https://twitter.com/
niklasluhmann
13. https://en.wikipedia.org/wiki/Ni
klas_Luhmann
Trust in Learning Analytics
• Data subjects face
uncertainty e.g. when
receiving outcomes of
learning analytics.
• Data subjects can not fully
understand the complexity
of learning analytics.
• Data subjects take a risk and
making oneself vulnerable
by feeding learning
analytics with personal data.
Following Luhmann, we define trust as a social phenomenon with the following
characteristics:
To gain trust from data subjects
we need to demonstrate
Transparency, Reliability, and
Integrity. As a return the data
subjects might ‘choose’ to trust
us.
14. 1. Definition of
trust and LA
2. Fears of
Learning
Analytics
4. Approaches
towards
Trusted Learning
Analytics
3. Human-
Centered
Design
Lecture structure
17. Keynote Neil Selwyn @ LAK 2018, Sydney, Australia
Learning Analytics has a trust problem …
Learning Analytics
18. … because Learning
Analytics has the potential
of becoming a high stakes
assessment.
Keynote Neil Selwyn @ LAK 2018, Sydney, Australia
Learning Analytics
19. Being in the next industrial revolution
means we are in an education system,
where the norms, relationships and
ways of teaching and learning are
impacted.
• Authority: Public -> Private
Influence and power are redistributed
• New (AI) actors:
Feedback to students from machines
• Data ownership:
Increased access for some may
mean reduced access for others
• False-truths:
Early products with simplistic
reasoning don’t represent what
learning is really about
https://commons.wikimedia.org/w
iki/File:Coalbrookdale_loco.jpg
Education in the
Industrial Revolution
20. Open algorithms
Transparent indicators
No automated decisions
Full access to data
Knowing who accesses your data
Feedback culture
Unknown algorithms
Unknown data collection
Automated decisions
No access to raw data
No control who uses it
Assessment culture
Black box vs. White box
21. • Right to be informed
• Right of access
• Right to rectification
• Right to erasure
• Right to restrict processing
• Right to data portability
• Right to object automated decision making
Do your Learning Technology systems
support these rights? Hands-up!
GDPR 2018
22. 1. Definition
of trust and
LA
2. Fears of
Learning
Analytics
4. Approaches
towards
Trusted Learning
Analytics
3. Human-
Centered
Design
Lecture structure
23. Some things
are already on its way
http://www.open.ac.uk/students/charter/ess
ential-documents/ethical-use-student-data-
learning-analytics-policy# https://www.jisc.ac.uk/sites/default/file
s/jd0040_code_of_practice_for_learni
ng_analytics_190515_v1.pdf
24. Drachsler, H. & Greller, W. (2016). Privacy and
Analytics – it’s a DELICATE issue. A Checklist
to establish trusted Learning Analytics. 6th
Learning Analytics and Knowledge Conference
2016, April 25-29, 2016, Edinburgh, UK.
Online at:
http://www.laceproject.eu/ethics-privacy/
Some things
are already on its way
25. http://www.sheilaproject.eu
Yi-Shan Tsai, Pedro Manuel
Moreno-Marcos, Kairit
Tammets, Kaire Kollom, and
Dragan Gašević. 2018.
SHEILA policy framework:
informing institutional
strategies and policy
processes of learning
analytics. In Proceedings of
the 8th International
Conference on Learning
Analytics and
Knowledge (LAK '18). ACM,
New York, NY, USA, 320-329.
DOI:
https://doi.org/10.1145/31703
58.3170367
Some things
are already on its way
There is no other Educational Technology discipline like
Learning Analytics that critically works on social
implications of their outcomes and addresses institutional
development.
26. 1. Definition
of trust and
LA
2. Fears of
Learning
Analytics
4. Approaches
towards
Trusted
Learning
Analytics
3. Human-
Centered
Design
Lecture structure
27. • Design-Based Research (DBR)
• AB– testing
Barab, S. A. (2014). Design-based research: a methodological toolkit for
engineering change. In K. Sawyer (ed.) Handbook of the Learning Sciences, Vol
2, (pp. 233-270), Cambridge, MA: Cambridge University Press.
Participatory Design-Process
29. • TLA is the first GDPR 2018
conform Big Data
infrastructure followed a
value-based design
approach
• Joined project with
GU, DIPF und OU
• Among ‘traditional‘ learning
data we also aim to collect
multimodal data.
Trusted Learning Analytics
Infrastructure
33. How to design your
Trusted Learning Analytics
TACTIC Cube
Trusted
Analytics
Cube
to
Teach
Institutional
Change
34. 35
Stakeholders
1. Interviews with students (n=46)
2. Survey on Learning Analytics (n=166)
3. Group Concept Mapping Study (n=101, 46)
4. Feedback from students, and teachers on dashboards
38. 39
Scheffel, M., Ternier, S., & Drachsler, H. (2016a). The Dutch xAPI Specification for Learning
Activities (DSLA) – Registry. Retrieved from http://bit.ly/DutchXAPIreg
http://www.laceproject.eu/blog/xapi-dsla/
Educational Data
40. 41
Verbert, K., Duval, E., Klerkx, J., Govaerts, S., & Santos, J. L. (2013). Learning
analytics dashboard applications. American Behavioral Scientist.
Technologies
42. Drachsler, H. & Greller,
W. (2016). Privacy and
Analytics – it’s a
DELICATE issue. A
Checklist to establish
trusted Learning
Analytics. LAK 2016,
April 25-29, Edinburgh,
UK.
Engelfriet, A., Jeunink,
E., Manderveld, J.
(2015). Learning
analytics onder de Wet
bescherming
persoonsgegevens
Constraints
44. 45
Interpretation skills
Drachsler, H., Stoyanov, S., d'Aquin, M., Herder, E., Dietze, S., & Guy, M. (2014, 16-19
September). An Evaluation Framework for Data Competitions in TEL. 9th European
Conference on Technology-Enhanced Learning (EC-TEL 2014), Graz, Austria.
49. Take home messages
1. We need to actively develop and apply learning
analytics tools to have informed discussion what are the
effects on the stakeholders.
2. We need participatory design approaches to involve
all stakeholders in learning analytics and train their
agency and data literacy skills.
3. We have an opportunity through the GDPR and the
stakeholder discourse in point 2 to design more
humanistic Trusted Learning Analytics.